Model Library
GoogleReleased April 2, 2026Gemma 4 31B
Google · Released April 2, 2026
Intelligence score
29
At a glance
- Intelligence
- 29
- Speed
- 34.4tokens/sec
- Latency
- 1.00stime to first token
- Input price
- Not published
- Output price
- Not published
- Context window
- 260Ktokens
- Parameters
- 30.7billions
Summary
Comparison summary
Gemma 4 31B (Reasoning) scores 29 on the Artificial Analysis Intelligence Index, placing it well above average among other open weight models of similar size (median: 9). Gemma 4 31B (Reasoning) generates output at 34.4 tokens per second (based on Google's API), which is at the lower end compared to other open weight models of similar size (median: 101.8 t/s).
Specifications
Technical specifications
| Model name | Gemma 4 31B |
|---|---|
| Provider | |
| Release date | April 2, 2026 |
| Intelligence score | 29 |
| Speed | 34.4 tokens/sec |
| Latency (TTFT) | 1.00s |
| Input price | Not published |
| Output price | Not published |
| Context window | 260,000 tokens |
| Parameters | 30.7B |
| Reasoning | Yes |
| Input modalities | text, image, video |
| Output modalities | — |
| Open weights | Yes |
| License | Apache 2 |
| API availability | — |
| Source | Model Intelligence legacy profile: gemma-4-31b |
FAQ · 18
Frequently asked questions
Gemma 4 31B (Reasoning) was released on April 2, 2026.
Gemma 4 31B (Reasoning) was created by Google.
Gemma 4 31B (Reasoning) scores 29 on the Artificial Analysis Intelligence Index, placing it well above average among other open weight models of similar size (median: 9).
Gemma 4 31B (Reasoning) generates output at 34.4 tokens per second (based on Google's API), which is at the lower end compared to other open weight models of similar size (median: 101.8 t/s).
Gemma 4 31B (Reasoning) has a time to first token (TTFT) of 1.00s (based on Google's API), which is better than average compared to other open weight models of similar size (median: 2.08s).
When evaluated on the Intelligence Index, Gemma 4 31B (Reasoning) generated 38M output tokens, which is somewhat higher than average compared to other open weight models of similar size (median: 32M).
Yes, Gemma 4 31B (Reasoning) is a reasoning model. It uses extended thinking or chain-of-thought reasoning to work through complex problems before providing an answer.
Gemma 4 31B (Reasoning) supports text, image, and video input.
Gemma 4 31B (Reasoning) supports text output.
Yes, Gemma 4 31B (Reasoning) supports image input and can analyze, describe, and answer questions about images.
Yes, Gemma 4 31B (Reasoning) is multimodal. It can process text, image, and video input and generate text output.
Gemma 4 31B (Reasoning) has a context window of 260k tokens. This determines how much text and conversation history the model can process in a single request.
Yes, Gemma 4 31B (Reasoning) is open weights. The model weights are publicly available and can be downloaded for self-hosting.
Gemma 4 31B (Reasoning) has 30.7 billion parameters.
Gemma 4 31B (Reasoning) is released under the Apache 2.0 license. This license allows commercial use.
Gemma 4 31B (Reasoning) achieves a score of 29 on the Artificial Analysis Intelligence Index. This composite benchmark evaluates models across reasoning, knowledge, mathematics, and coding.
Yes, Gemma 4 31B (Reasoning) is available via API through 12 providers.
Gemma 4 31B (Reasoning) is available through 12 API providers.